Feature map sharing hypercolumn model for shift invariant face recognition

Saleh Aly, Naoyuki Tsuruta, Rin-Ichiro Taniguchi

Research output: Contribution to journalArticle

Abstract

In this article, we propose a shift-invariant pattern recognition mechanism using a feature-sharing hypercolumn model (FSHCM). To improve the recognition rate and to reduce the memory requirements of the hypercolumn model (HCM), a shared map is constructed to replace a set of local neighborhood maps in the feature extraction and feature integration layers. The shared maps increase the ability of the network to deal with translation and distortion variations in the input image. The proposed face recognition system employed a FSHCM neural network to perform feature extraction and use a linear support vector machine for a recognition task. The effectiveness of the proposed approach is verified by measuring the recognition accuracy using the misaligned ORL face database.

Original languageEnglish
Pages (from-to)271-274
Number of pages4
JournalArtificial Life and Robotics
Volume14
Issue number2
DOIs
Publication statusPublished - Nov 1 2009

Fingerprint

Neural Networks (Computer)
Face recognition
Databases
Feature extraction
Pattern recognition
Support vector machines
Neural networks
Data storage equipment
Facial Recognition
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

Cite this

Feature map sharing hypercolumn model for shift invariant face recognition. / Aly, Saleh; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

In: Artificial Life and Robotics, Vol. 14, No. 2, 01.11.2009, p. 271-274.

Research output: Contribution to journalArticle

@article{8b747fbb099c48a6bf8555168f1bbf38,
title = "Feature map sharing hypercolumn model for shift invariant face recognition",
abstract = "In this article, we propose a shift-invariant pattern recognition mechanism using a feature-sharing hypercolumn model (FSHCM). To improve the recognition rate and to reduce the memory requirements of the hypercolumn model (HCM), a shared map is constructed to replace a set of local neighborhood maps in the feature extraction and feature integration layers. The shared maps increase the ability of the network to deal with translation and distortion variations in the input image. The proposed face recognition system employed a FSHCM neural network to perform feature extraction and use a linear support vector machine for a recognition task. The effectiveness of the proposed approach is verified by measuring the recognition accuracy using the misaligned ORL face database.",
author = "Saleh Aly and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2009",
month = "11",
day = "1",
doi = "10.1007/s10015-009-0669-y",
language = "English",
volume = "14",
pages = "271--274",
journal = "Artificial Life and Robotics",
issn = "1433-5298",
publisher = "Springer Japan",
number = "2",

}

TY - JOUR

T1 - Feature map sharing hypercolumn model for shift invariant face recognition

AU - Aly, Saleh

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2009/11/1

Y1 - 2009/11/1

N2 - In this article, we propose a shift-invariant pattern recognition mechanism using a feature-sharing hypercolumn model (FSHCM). To improve the recognition rate and to reduce the memory requirements of the hypercolumn model (HCM), a shared map is constructed to replace a set of local neighborhood maps in the feature extraction and feature integration layers. The shared maps increase the ability of the network to deal with translation and distortion variations in the input image. The proposed face recognition system employed a FSHCM neural network to perform feature extraction and use a linear support vector machine for a recognition task. The effectiveness of the proposed approach is verified by measuring the recognition accuracy using the misaligned ORL face database.

AB - In this article, we propose a shift-invariant pattern recognition mechanism using a feature-sharing hypercolumn model (FSHCM). To improve the recognition rate and to reduce the memory requirements of the hypercolumn model (HCM), a shared map is constructed to replace a set of local neighborhood maps in the feature extraction and feature integration layers. The shared maps increase the ability of the network to deal with translation and distortion variations in the input image. The proposed face recognition system employed a FSHCM neural network to perform feature extraction and use a linear support vector machine for a recognition task. The effectiveness of the proposed approach is verified by measuring the recognition accuracy using the misaligned ORL face database.

UR - http://www.scopus.com/inward/record.url?scp=72449180019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449180019&partnerID=8YFLogxK

U2 - 10.1007/s10015-009-0669-y

DO - 10.1007/s10015-009-0669-y

M3 - Article

VL - 14

SP - 271

EP - 274

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 2

ER -